General-Science
LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost
Microbenchmarking NVIDIA's Blackwell Architecture: An in-depth Architectural Analysis
Model Recovery at the Edge under Resource Constraints for Physical AI
Neural Network Optimal Power Flow via Energy Gradient Flow and Unified Dynamics
Order-Disorder in Fe-Si Alloys: Implications for Seismic Anisotropy and Thermal Evolution of Earth's Inner Core
Physics-Constrained Neural Dynamics: A Unified Manifold Framework for Large-Scale Power Flow Computation
Physics-Informed Neural Networks for Thermophysical Property Retrieval
Progressive Image Restoration via Text-Conditioned Video Generation
Real-World Reinforcement Learning of Active Perception Behaviors
Rethinking Intracranial Aneurysm Vessel Segmentation: A Perspective from Computational Fluid Dynamics Applications
RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions
Social Media Data Mining of Human Behaviour during Bushfire Evacuation
Solving Context Window Overflow in AI Agents
Switching-time bioprocess control with pulse-width-modulated optogenetics
Teaching by Failure: Counter-Example-Driven Curricula for Transformer Self-Improvement
Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives
Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion
What If They Took the Shot? A Hierarchical Bayesian Framework for Counterfactual Expected Goals
Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems
Young children's anthropomorphism of an AI chatbot: Brain activation and the role of parent co-presence